PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors
In this paper we propose a new approach for learning local descriptors for matching image patches. It has recently been demonstrated that descriptors based on convolutional neural networks (CNN) can significantly improve the matching performance. Unfortunately their computational complexity is prohibitive for any practical application. We address this problem and propose a CNN based descriptor with improved matching performance, significantly reduced training and execution time, as well as low dimensionality. We propose to train the network with triplets of patches that include a positive and negative pairs. To that end we introduce a new loss function that exploits the relations within the triplets. We compare our approach to recently introduced MatchNet and DeepCompare and demonstrate the advantages of our descriptor in terms of performance, memory footprint and speed i.e. when run in GPU, the extraction time of our 128 dimensional feature is comparable to the fastest available binary descriptors such as BRIEF and ORB.
Code (1)
Tasks
GPUMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TCDesc: Learning Topology Consistent Descriptors
Triplet loss is widely used for learning local descriptors from image patch. However, triplet loss only minimizes the Euclidean distance between matching descriptors and maximizes that between the non-matching descriptor…
TripletLearning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions
Recent innovations in training deep convolutional neural network (ConvNet) models have motivated the design of new methods to automatically learn local image descriptors. The latest deep ConvNets proposed for this task c…
General ClassificationTripletLearning 3D Keypoint Descriptors for Non-Rigid Shape Matching
In this paper, we present a novel deep learning framework that derives discriminative local descriptors for 3D surface shapes. In contrast to previous convolutional neural networks (CNNs) that rely on rendering multi-vie…
Metric LearningTripletLearning Spread-out Local Feature Descriptors
We propose a simple, yet powerful regularization technique that can be used to significantly improve both the pairwise and triplet losses in learning local feature descriptors. The idea is that in order to fully utilize …
TripletLearning local feature descriptors with triplets and shallow convolutional neural networks
It has recently been demonstrated that local feature descriptors based on convolutional neural networks (CNN) can significantly improve the matching performance. Previous work on learning such descriptors has focused o…
Triplet